Machine learning methods strive to acquire a robust model during training that can generalize well to test samples, even under distribution shifts. However, these methods often suffer from a performance drop due to unknown test distributions. Test-time adaptation (TTA), an emerging paradigm, has the potential to adapt a pre-trained model to unlabeled data during testing, before making predictions. Recent progress in this paradigm highlights the significant benefits of utilizing unlabeled data for training self-adapted models prior to inference. In this survey, we divide TTA into several distinct categories, namely, test-time (source-free) domain adaptation, test-time batch adaptation, online test-time adaptation, and test-time prior adaptation. For each category, we provide a comprehensive taxonomy of advanced algorithms, followed by a discussion of different learning scenarios. Furthermore, we analyze relevant applications of TTA and discuss open challenges and promising areas for future research. A comprehensive list of TTA methods can be found at \url{https://github.com/tim-learn/awesome-test-time-adaptation}.

翻译：机器学习方法致力于在训练过程中获取鲁棒模型，使其即使在分布偏移下也能对测试样本具有良好的泛化能力。然而，由于测试分布未知，这些方法常常面临性能下降的问题。测试时自适应（TTA）作为一种新兴范式，能够在测试阶段、预测之前将预训练模型适应于未标记数据。该范式的最新进展表明，在推理前利用未标记数据训练自适应模型具有显著优势。在本综述中，我们将TTA分为几个不同类别，即测试时（无源）域自适应、测试时批量自适应、在线测试时自适应和测试时先验自适应。针对每个类别，我们提供了先进算法的全面分类，并讨论了不同的学习场景。此外，我们分析了TTA的相关应用，并探讨了开放挑战和未来研究的潜在方向。TTA方法的完整列表可参见\url{https://github.com/tim-learn/awesome-test-time-adaptation}。